Recent advances in Large Language Models (LLMs) have enabled the creation of
Recent advances in Large Language Models (LLMs) have enabled the creation of Generative Agents (GAs) capable of autonomous decision-making in interaction. This paper investigates whether GAs can exhibit socially credible behavior. Drawing from behavioral game theory, we evaluate five state-of-the-art models across three canonical game-theoretic environments. Our results show that, while some GAs can accurately predict their opponent’s behavior, few are able to incorporate those predictions into decision-making. These behavioral flaws help explain why coordination remains especially challenging: most models struggle to align with others, even when communication is allowed.
Generative Agents (GAs) capable of autonomous decision-making in interactive
settings. This paper investigates whether GAs can exhibit socially credible
behavior. Drawing from behavioral game theory, we evaluate five state-of-the-art
models across three canonical game-theoretic environments. Our results show that
while some GAs can accurately predict their opponent’s behavior, few are able to
incorporate those predictions into decision-making. These behavioral flaws help
explain why coordination remains especially challenging: most models struggle to
align with others, even when communication is allowed.
